INDEX

Explanations

positive recommendations for services or products

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SequentialGroup

-0.67

 >=",

-0.66

AddTagHelper

-0.61

testens

-0.59

AsUp

-0.57

 لينك

-0.57

+#+

-0.56

 Anſ

-0.55

AddHtmlAttribute

-0.55

findpost

-0.55

POSITIVE LOGITS

ThroughAttribute

0.59

 Recommend

0.57

neté

0.57

HomeAsUpEnabled

0.56

 recommend

0.54

 متعلقه

0.52

 recommending

0.52

//

0.52

 OMITBAD

0.52

Recommend

0.51

Activations Density 0.112%

positive recommendations for services or products

No Comments

No Known Activations